Related papers: DriveGen3D: Boosting Feed-Forward Driving Scene Ge…
Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…
With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required.…
Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception models. However, existing approaches often struggle with…
Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout…
Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small…
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…
3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on…
Real-time, high-fidelity reconstruction of dynamic driving scenes is challenged by complex dynamics and sparse views, with prior methods struggling to balance quality and efficiency. We propose DrivingScene, an online, feed-forward…
Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…
Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability…
Generating multi-camera street-view videos is critical for augmenting autonomous driving datasets, addressing the urgent demand for extensive and varied data. Due to the limitations in diversity and challenges in handling lighting…
Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…
3D content generation has recently attracted significant research interest, driven by its critical applications in VR/AR and embodied AI. In this work, we tackle the challenging task of synthesizing multiple 3D assets within a single scene…
In autonomous driving, vision-centric 3D detection aims to identify 3D objects from images. However, high data collection costs and diverse real-world scenarios limit the scale of training data. Once distribution shifts occur between…
Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on…
Diffusion models are advancing autonomous driving by enabling realistic data synthesis, predictive end-to-end planning, and closed-loop simulation, with a primary focus on temporally consistent generation. However, large-scale 3D scene…
Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate…
Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting…
A recent frontier in computer vision has been the task of 3D video generation, which consists of generating a time-varying 3D representation of a scene. To generate dynamic 3D scenes, current methods explicitly model 3D temporal dynamics by…
Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. Bridging generation and novel view…